search_all_knowledge
Search ALL accumulated knowledge in one call: learnings (edge cases, gotchas, patterns), recon findings (across ALL sessions), and resolved gaps from past verifications. Use this before starting any new work to see what the system already knows. This is the unified knowledge base that grows autom...
This record as markdown: /tools/io-github-homenshum-nodebench/search-all-knowledge.md
What search_all_knowledge does on Nodebench
AI agents call search_all_knowledge to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why search_all_knowledge is rated Low
This tool performs read-only operations against a knowledge base. It searches and retrieves accumulated learnings, recon findings, and resolved gaps without modifying, creating, deleting, or executing any operations. The verb 'search' and the stated purpose of viewing existing knowledge confirm this is a Read category tool.
From the tool's definition Tool description explicitly states 'Search ALL accumulated knowledge' and 'Use this before starting any new work to see what the system already knows.' The action is purely retrieving/querying existing data with no side effects.
Attacks that exploit this kind of access
The rule that runs search_all_knowledge safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search_all_knowledge, this is the rule to start with:
search_all_knowledge is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every search_all_knowledge call is checked against it from then on.
Questions about search_all_knowledge
Search ALL accumulated knowledge in one call: learnings (edge cases, gotchas, patterns), recon findings (across ALL sessions), and resolved gaps from past verifications. Use this before starting any new work to see what the system already knows. This is the unified knowledge base that grows automatically as the tools are used. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for search_all_knowledge: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nodebench. Nothing to install.
search_all_knowledge is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_all_knowledge rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_all_knowledge. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_all_knowledge is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue